English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Molecular dynamics simulations have emerged as a potent tool forinvestigating the physical properties and kinetic behaviors of materials at theatomic scale, particularly in extreme conditions. Ab initio accuracy is nowachievable with machine learning based interatomic potentials. With recentadvancements in high-performance computing, highly accurate and large-scalesimulations become feasible. This study introduces TensorMD, a new machinelearning interatomic potential (MLIP) model that integrates physical principlesand tensor diagrams. The tensor formalism provides a more efficient computationand greater flexibility for use with other scientific codes. Additionally, weproposed several portable optimization strategies and developed a highlyoptimized version for the new Sunway supercomputer. Our optimized TensorMD canachieve unprecedented performance on the new Sunway, enabling simulations of upto 52 billion atoms with a time-to-solution of 31 ps/step/atom, setting newrecords for HPC + AI + MD.

TensorMD: Scalable Tensor-Diagram based Machine Learning Interatomic Potential on Heterogeneous Many-Core Processors